Generating multi-view images based on text or single-image prompts is a critical capability for the creation of 3D content. Two fundamental questions on this topic are what data we use for training and how to ensure multi-view consistency. This paper introduces a novel framework that makes fundamental contributions to both questions. Unlike leveraging images from 2D diffusion models for training, we propose a dense consistent multi-view generation model that is fine-tuned from off-the-shelf video generative models. Images from video generative models are more suitable for multi-view generation because the underlying network architecture that generates them employs a temporal module to enforce frame consistency. Moreover, the video data sets used to train these models are abundant and diverse, leading to a reduced train-finetuning domain gap. To enhance multi-view consistency, we introduce a 3D-Aware Denoising Sampling, which first employs a feed-forward reconstruction module to get an explicit global 3D model, and then adopts a sampling strategy that effectively involves images rendered from the global 3D model into the denoising sampling loop to improve the multi-view consistency of the final images. As a by-product, this module also provides a fast way to create 3D assets represented by 3D Gaussians within a few seconds. Our approach can generate 24 dense views and converges much faster in training than state-of-the-art approaches (4 GPU hours versus many thousand GPU hours) with comparable visual quality and consistency. By further fine-tuning, our approach outperforms existing state-of-the-art methods in both quantitative metrics and visual effects. Our project page is aigc3d.github.io/VideoMV.
Device-free wireless sensing attracts enormous attentions since it senses the environment without additional devices. While cellular signals are good opportunistic radio sources, the influence of inter-cell interference (ICI) on wireless sensing has not been adequately addressed. In this letter, we first investigate the cause of ICI and its impact on wireless sensing. Then we propose an ICI-free channel estimation method by reconstructing the broadcast signals of adjacent cells and solving simultaneous equations. Wireless gesture recognition can be greatly benefited by ICI mitigation. Finally, we build a prototype system to receive the commercial 4G-LTE signals, and demonstrate the accuracies of wireless gesture recognition under various conditions.
IMPORTANCE The response effectiveness of different large language models (LLMs) and various individuals, including medical students, graduate students, and practicing physicians, in pediatric ophthalmology consultations, has not been clearly established yet. OBJECTIVE Design a 100-question exam based on pediatric ophthalmology to evaluate the performance of LLMs in highly specialized scenarios and compare them with the performance of medical students and physicians at different levels. DESIGN, SETTING, AND PARTICIPANTS This survey study assessed three LLMs, namely ChatGPT (GPT-3.5), GPT-4, and PaLM2, were assessed alongside three human cohorts: medical students, postgraduate students, and attending physicians, in their ability to answer questions related to pediatric ophthalmology. It was conducted by administering questionnaires in the form of test papers through the LLM network interface, with the valuable participation of volunteers. MAIN OUTCOMES AND MEASURES Mean scores of LLM and humans on 100 multiple-choice questions, as well as the answer stability, correlation, and response confidence of each LLM. RESULTS GPT-4 performed comparably to attending physicians, while ChatGPT (GPT-3.5) and PaLM2 outperformed medical students but slightly trailed behind postgraduate students. Furthermore, GPT-4 exhibited greater stability and confidence when responding to inquiries compared to ChatGPT (GPT-3.5) and PaLM2. CONCLUSIONS AND RELEVANCE Our results underscore the potential for LLMs to provide medical assistance in pediatric ophthalmology and suggest significant capacity to guide the education of medical students.
This paper outlines the winning solutions employed in addressing the MUAD uncertainty quantification challenge held at ICCV 2023. The challenge was centered around semantic segmentation in urban environments, with a particular focus on natural adversarial scenarios. The report presents the results of 19 submitted entries, with numerous techniques drawing inspiration from cutting-edge uncertainty quantification methodologies presented at prominent conferences in the fields of computer vision and machine learning and journals over the past few years. Within this document, the challenge is introduced, shedding light on its purpose and objectives, which primarily revolved around enhancing the robustness of semantic segmentation in urban scenes under varying natural adversarial conditions. The report then delves into the top-performing solutions. Moreover, the document aims to provide a comprehensive overview of the diverse solutions deployed by all participants. By doing so, it seeks to offer readers a deeper insight into the array of strategies that can be leveraged to effectively handle the inherent uncertainties associated with autonomous driving and semantic segmentation, especially within urban environments.
The SoccerNet 2023 challenges were the third annual video understanding challenges organized by the SoccerNet team. For this third edition, the challenges were composed of seven vision-based tasks split into three main themes. The first theme, broadcast video understanding, is composed of three high-level tasks related to describing events occurring in the video broadcasts: (1) action spotting, focusing on retrieving all timestamps related to global actions in soccer, (2) ball action spotting, focusing on retrieving all timestamps related to the soccer ball change of state, and (3) dense video captioning, focusing on describing the broadcast with natural language and anchored timestamps. The second theme, field understanding, relates to the single task of (4) camera calibration, focusing on retrieving the intrinsic and extrinsic camera parameters from images. The third and last theme, player understanding, is composed of three low-level tasks related to extracting information about the players: (5) re-identification, focusing on retrieving the same players across multiple views, (6) multiple object tracking, focusing on tracking players and the ball through unedited video streams, and (7) jersey number recognition, focusing on recognizing the jersey number of players from tracklets. Compared to the previous editions of the SoccerNet challenges, tasks (2-3-7) are novel, including new annotations and data, task (4) was enhanced with more data and annotations, and task (6) now focuses on end-to-end approaches. More information on the tasks, challenges, and leaderboards are available on https://www.soccer-net.org. Baselines and development kits can be found on https://github.com/SoccerNet.
This paper addresses the problem of traversing through unknown, tilted, and narrow gaps for quadrotors using Deep Reinforcement Learning (DRL). Previous learning-based methods relied on accurate knowledge of the environment, including the gap's pose and size. In contrast, we integrate onboard sensing and detect the gap from a single onboard camera. The training problem is challenging for two reasons: a precise and robust whole-body planning and control policy is required for variable-tilted and narrow gaps, and an effective Sim2Real method is needed to successfully conduct real-world experiments. To this end, we propose a learning framework for agile gap traversal flight, which successfully trains the vehicle to traverse through the center of the gap at an approximate attitude to the gap with aggressive tilted angles. The policy trained only in a simulation environment can be transferred into different domains with fine-tuning while maintaining the success rate. Our proposed framework, which integrates onboard sensing and a neural network controller, achieves a success rate of 84.51% in real-world experiments, with gap orientations up to 60deg. To the best of our knowledge, this is the first paper that performs the learning-based variable-tilted narrow gap traversal flight in the real world, without prior knowledge of the environment.
Depth estimation is solved as a regression or classification problem in existing learning-based multi-view stereo methods. Although these two representations have recently demonstrated their excellent performance, they still have apparent shortcomings, e.g., regression methods tend to overfit due to the indirect learning cost volume, and classification methods cannot directly infer the exact depth due to its discrete prediction. In this paper, we propose a novel representation, termed Unification, to unify the advantages of regression and classification. It can directly constrain the cost volume like classification methods, but also realize the sub-pixel depth prediction like regression methods. To excavate the potential of unification, we design a new loss function named Unified Focal Loss, which is more uniform and reasonable to combat the challenge of sample imbalance. Combining these two unburdened modules, we present a coarse-to-fine framework, that we call UniMVSNet. The results of ranking first on both DTU and Tanks and Temples benchmarks verify that our model not only performs the best but also has the best generalization ability.
Aerial robotic systems has raised emerging interests among researchers. In this paper, a novel aerial manipulation system: a flying continuum robotic manipulator (AeCoM) is first proposed, to the best of authors' knowledge. In the perspective of design, a lightweight tendon-driven continuum robotic arm (in 3D-printed material) is delicately coupled with a quadrotor. To address the problem of kinematics inaccuracy due to different tip loading, we introduce an attitude sensor (IMU) to assist in PCC (Piecewise Constant Curvature) configuration. To deal with frequent and complex aerial manipulation tasks, we deploy a tension-based closed-loop control method, which is used to avoid tendon-slacking in manipulating the shape of the continuum arm. Distinct from the conventional aerial rigid manipulators, the proposed system achieve more relative payload capability and motion dexterity. The system's experimental results validate the performance of tendon-slacking avoidance, kinematics accuracy with different tip loading, and tip positioning accuracy for aerial grasping. The comparison with conventional aerial manipulators, indicates that the proposed manipulator has better manipulation performance and more potential applications in the cluttered environment.
Self-supervised methods play an increasingly important role in monocular depth estimation due to their great potential and low annotation cost. To close the gap with supervised methods, recent works take advantage of extra constraints, e.g., semantic segmentation. However, these methods will inevitably increase the burden on the model. In this paper, we show theoretical and empirical evidence that the potential capacity of self-supervised monocular depth estimation can be excavated without increasing this cost. In particular, we propose (1) a novel data augmentation approach called data grafting, which forces the model to explore more cues to infer depth besides the vertical image position, (2) an exploratory self-distillation loss, which is supervised by the self-distillation label generated by our new post-processing method - selective post-processing, and (3) the full-scale network, designed to endow the encoder with the specialization of depth estimation task and enhance the representational power of the model. Extensive experiments show that our contributions can bring significant performance improvement to the baseline with even less computational overhead, and our model, named EPCDepth, surpasses the previous state-of-the-art methods even those supervised by additional constraints.
This paper presents a point cloud based robotic system for arc welding. Using hand gesture controls, the system scans partial point cloud views of workpiece and reconstructs them into a complete 3D model by a linear iterative closest point algorithm. Then, a bilateral filter is extended to denoise the workpiece model and preserve important geometrical information. To extract the welding seam from the model, a novel intensity-based algorithm is proposed that detects edge points and generates a smooth 6-DOF welding path. The methods are tested on multiple workpieces with different joint types and poses. Experimental results prove the robustness and efficiency of this robotic system on automatic path planning for welding applications.